feat(backend): add magpie-tts-cpp text-to-speech backend (#11115)

* feat(backend): add magpie-tts-cpp text-to-speech backend Add a Go + purego backend wrapping the magpie-tts.cpp ggml port of NVIDIA's Magpie TTS Multilingual 357M (encoder + autoregressive decoder over NanoCodec tokens), producing 22.05 kHz mono audio in 5 baked voices (Aria, Jason, John, Leo, Sofia; case-insensitive names or indices 0-4) across 9+ languages from a single self-contained GGUF. Mirrors qwen3-tts-cpp / moss-tts-cpp: dlopen the static-ggml shared library, bind the flat magpie_tts_capi_* C-API via purego (no local C shim needed, the upstream .so exports it directly), and serve the gRPC TTS + TTSStream methods behind base.SingleThread (the C context is not reentrant across synthesize calls). The backend CMakeLists translates the Makefile's -DGGML_{CUDA,METAL,VULKAN,HIP} flags into upstream's MAGPIE_GGML_* toggles (upstream FORCE-overwrites the ggml cache entries from those), pinned to magpie-tts.cpp v0.1.1 (e3f3dd1ebe22b64e7405f93b519f2d1930712568), which statically links ggml into libmagpie-tts.so (ldd shows only system libs). Wires the full registration: backend-matrix.yml (CPU amd64/arm64, CUDA 12/13, Intel SYCL f16/f32, Vulkan amd64/arm64, ROCm, NVIDIA L4T + L4T CUDA 13, and Darwin metal), backend/index.yaml metas and image entries, the root Makefile build targets, the changed-backends backend-filter path mapping, the bump_deps auto-bump matrix, a test-extra per-backend smoke job, the /backends/known pref-only importer entry, the backend capabilities map (TTS + TTSStream, no voice cloning), and the README / compatibility-table docs rows. Verified locally: unit + e2e Ginkgo suites pass against the real q8_0 GGUF (22.05 kHz mono WAV, RMS > 0.01), a live gRPC LoadModel + TTS round-trip returns valid non-silent audio, and the pre-commit gates (make lint, make test-coverage-check) pass, run manually with LOCALAI_TEST_HTTP_PORT overriding the locally-occupied 9090. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * gallery: add magpie-tts-cpp model entries (q8_0 + f16) Add the Magpie TTS Multilingual 357M GGUFs from mudler/magpie-tts.cpp-gguf to the model gallery: q8_0 (~624 MB, near-lossless, fastest decode, recommended) with an f16 (~784 MB) variant, both served by the magpie-tts-cpp backend. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * magpie-tts-cpp: bump pin to rewritten upstream v0.1.1 SHA Upstream history was rewritten to purge accidentally committed build artifacts; v0.1.1 now resolves to 6f7696cf. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-30 09:57:57 -04:00 · 2026-07-25 08:38:48 +02:00
parent 130daa0c55
commit 2d889e61a6
25 changed files with 1451 additions and 2 deletions
--- a/.github/backend-matrix.yml
+++ b/.github/backend-matrix.yml
@@ -871,6 +871,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-magpie-tts-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'cublas'
    cuda-major-version: "12"
    cuda-minor-version: "8"
@@ -1935,6 +1948,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-magpie-tts-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'cublas'
    cuda-major-version: "13"
    cuda-minor-version: "0"
@@ -2000,6 +2026,19 @@ include:
    backend: "moss-tts-cpp"
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
  - build-type: 'cublas'
    cuda-major-version: "13"
    cuda-minor-version: "0"
@@ -4583,6 +4622,20 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-magpie-tts-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: ''
    cuda-major-version: ""
    cuda-minor-version: ""
@@ -4598,6 +4651,20 @@ include:
    context: "./"
    ubuntu-version: '2404'
  # omnivoice-cpp
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-magpie-tts-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: ''
    cuda-major-version: ""
    cuda-minor-version: ""
@@ -4652,6 +4719,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-magpie-tts-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'sycl_f32'
    cuda-major-version: ""
    cuda-minor-version: ""
@@ -4691,6 +4771,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-magpie-tts-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'sycl_f16'
    cuda-major-version: ""
    cuda-minor-version: ""
@@ -4732,6 +4825,20 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-magpie-tts-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'vulkan'
    cuda-major-version: ""
    cuda-minor-version: ""
@@ -4774,6 +4881,20 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-magpie-tts-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'vulkan'
    cuda-major-version: ""
    cuda-minor-version: ""
@@ -4814,6 +4935,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2204'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-magpie-tts-cpp'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
  - build-type: 'cublas'
    cuda-major-version: "12"
    cuda-minor-version: "0"
@@ -4853,6 +4987,19 @@ include:
    dockerfile: "./backend/Dockerfile.golang"
    context: "./"
    ubuntu-version: '2404'
+  - build-type: 'hipblas'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-rocm-hipblas-magpie-tts-cpp'
+    base-image: "rocm/dev-ubuntu-24.04:6.4.4"
+    runs-on: 'ubuntu-latest'
+    skip-drivers: 'false'
+    backend: "magpie-tts-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
  - build-type: 'hipblas'
    cuda-major-version: ""
    cuda-minor-version: ""
@@ -5774,6 +5921,10 @@ includeDarwin:
    tag-suffix: "-metal-darwin-arm64-moss-tts-cpp"
    build-type: "metal"
    lang: "go"
+  - backend: "magpie-tts-cpp"
+    tag-suffix: "-metal-darwin-arm64-magpie-tts-cpp"
+    build-type: "metal"
+    lang: "go"
  - backend: "omnivoice-cpp"
    tag-suffix: "-metal-darwin-arm64-omnivoice-cpp"
    build-type: "metal"
--- a/.github/workflows/bump_deps.yaml
+++ b/.github/workflows/bump_deps.yaml
@@ -110,6 +110,10 @@ jobs:
            variable: "VIBEVOICE_CPP_VERSION"
            branch: "master"
            file: "backend/go/vibevoice-cpp/Makefile"
+          - repository: "mudler/magpie-tts.cpp"
+            variable: "MAGPIETTS_CPP_VERSION"
+            branch: "main"
+            file: "backend/go/magpie-tts-cpp/Makefile"
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7
--- a/.github/workflows/test-extra.yml
+++ b/.github/workflows/test-extra.yml
@@ -37,6 +37,7 @@ jobs:
      sglang: ${{ steps.detect.outputs.sglang }}
      acestep-cpp: ${{ steps.detect.outputs.acestep-cpp }}
      qwen3-tts-cpp: ${{ steps.detect.outputs.qwen3-tts-cpp }}
+      magpie-tts-cpp: ${{ steps.detect.outputs.magpie-tts-cpp }}
      rfdetr-cpp: ${{ steps.detect.outputs.rfdetr-cpp }}
      locate-anything-cpp: ${{ steps.detect.outputs.locate-anything-cpp }}
      vibevoice-cpp: ${{ steps.detect.outputs.vibevoice-cpp }}
@@ -866,6 +867,38 @@ jobs:
      - name: Test qwen3-tts-cpp
        run: |
          make --jobs=5 --output-sync=target -C backend/go/qwen3-tts-cpp test
+  tests-magpie-tts-cpp:
+    needs: detect-changes
+    if: needs.detect-changes.outputs.magpie-tts-cpp == 'true' || needs.detect-changes.outputs.run-all == 'true'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Clone
+        uses: actions/checkout@v7
+        with:
+          submodules: true
+      - name: Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential cmake curl libopenblas-dev ffmpeg
+      - name: Setup Go
+        uses: actions/setup-go@v5
+      - name: Display Go version
+        run: go version
+      - name: Proto Dependencies
+        run: |
+          # Install protoc
+          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
+          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
+          rm protoc.zip
+          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
+          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+          PATH="$PATH:$HOME/go/bin" make protogen-go
+      - name: Build magpie-tts-cpp
+        run: |
+          make --jobs=5 --output-sync=target -C backend/go/magpie-tts-cpp
+      - name: Test magpie-tts-cpp
+        run: |
+          make --jobs=5 --output-sync=target -C backend/go/magpie-tts-cpp test
  # Per-backend smoke for rfdetr-cpp: builds the .so + Go binary and runs
  # `make -C backend/go/rfdetr-cpp test`. test.sh fetches the small (~20 MB)
  # rfdetr-nano-q8_0 GGUF from the published mudler/rfdetr-cpp-nano HF repo
--- a/6
+++ b/6
@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/bonsai backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/crispasr backends/parakeet-cpp backends/moss-transcribe-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/cloud-proxy backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/longcat-video backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/moss-tts-cpp backends/omnivoice-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio backends/supertonic backends/depth-anything-cpp backends/privacy-filter backends/privacy-filter-darwin
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/bonsai backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/crispasr backends/parakeet-cpp backends/moss-transcribe-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/cloud-proxy backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/longcat-video backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/moss-tts-cpp backends/magpie-tts-cpp backends/omnivoice-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio backends/supertonic backends/depth-anything-cpp backends/privacy-filter backends/privacy-filter-darwin

 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -1257,6 +1257,7 @@ BACKEND_VOXTRAL = voxtral|golang|.|false|true
 BACKEND_ACESTEP_CPP = acestep-cpp|golang|.|false|true
 BACKEND_QWEN3_TTS_CPP = qwen3-tts-cpp|golang|.|false|true
 BACKEND_MOSS_TTS_CPP = moss-tts-cpp|golang|.|false|true
+BACKEND_MAGPIE_TTS_CPP = magpie-tts-cpp|golang|.|false|true
 BACKEND_OMNIVOICE_CPP = omnivoice-cpp|golang|.|false|true
 BACKEND_VIBEVOICE_CPP = vibevoice-cpp|golang|.|false|true
 BACKEND_LOCALVQE = localvqe|golang|.|false|true
@@ -1384,6 +1385,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_ACE_STEP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_ACESTEP_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_QWEN3_TTS_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_MOSS_TTS_CPP)))
+$(eval $(call generate-docker-build-target,$(BACKEND_MAGPIE_TTS_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_OMNIVOICE_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_VIBEVOICE_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_LOCALVQE)))
@@ -1403,7 +1405,7 @@ $(eval $(call generate-docker-build-target,$(BACKEND_SUPERTONIC)))
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar

-docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-bonsai docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-longcat-video docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-crispasr docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-rfdetr-cpp docker-build-qwen3-tts-cpp docker-build-moss-tts-cpp docker-build-omnivoice-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy docker-build-supertonic docker-build-depth-anything-cpp docker-build-moss-transcribe-cpp docker-build-privacy-filter
+docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-bonsai docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-longcat-video docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-crispasr docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-rfdetr-cpp docker-build-qwen3-tts-cpp docker-build-moss-tts-cpp docker-build-magpie-tts-cpp docker-build-omnivoice-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy docker-build-supertonic docker-build-depth-anything-cpp docker-build-moss-transcribe-cpp docker-build-privacy-filter

 ########################################################
 ### Mock Backend for E2E Tests
--- a/README.md
+++ b/README.md
@@ -234,6 +234,7 @@ Most backends wrap a best-in-class upstream engine. A handful of them are native
 | [parakeet.cpp](https://github.com/mudler/parakeet.cpp) | C++/GGML port of NVIDIA NeMo Parakeet ASR (tdt/ctc/rnnt/hybrid), with cache-aware streaming transcription |
 | [moss-transcribe.cpp](https://github.com/localai-org/moss-transcribe.cpp) | C++/GGML port of OpenMOSS MOSS-Transcribe-Diarize: joint long-form transcription, speaker diarization and timestamping in a single pass |
 | [moss-tts.cpp](https://github.com/mudler/moss-tts.cpp) | C++/GGML port of the OpenMOSS MOSS-TTS family: text-to-speech (MOSS-TTS-Local v1.5, 48 kHz stereo) with reference-audio voice cloning, through the MOSS-Audio-Tokenizer neural codec |
+| [magpie-tts.cpp](https://github.com/mudler/magpie-tts.cpp) | C++/GGML port of NVIDIA's Magpie TTS Multilingual 357M: 22.05 kHz mono text-to-speech in 5 voices and 9+ languages, with the NanoCodec neural codec and tokenizer/G2P embedded in a single GGUF |
 | [ced.cpp](https://github.com/localai-org/ced.cpp) | C++/GGML port of the CED audio-tagging models: sound-event classification (527-class AudioSet) over REST and the realtime API for live recognition |
 | [voice-detect.cpp](https://github.com/localai-org/voice-detect.cpp) | Speaker recognition and voice analysis (ECAPA-TDNN, WeSpeaker, ERes2Net, CAM++, wav2vec2 age/gender/emotion), replacing the Python speaker-recognition backend |
 | [voxtral-tts.c](https://github.com/mudler/voxtral-tts.c) | Voxtral Realtime 4B speech-to-text in pure C |
--- a/backend/go/magpie-tts-cpp/.gitignore
+++ b/backend/go/magpie-tts-cpp/.gitignore
@@ -0,0 +1,6 @@
+magpie-tts-cpp
+*.so
+*.dylib
+sources/
+package/
+magpie-tts-models/
--- a/backend/go/magpie-tts-cpp/CMakeLists.txt
+++ b/backend/go/magpie-tts-cpp/CMakeLists.txt
@@ -0,0 +1,35 @@
+cmake_minimum_required(VERSION 3.16)
+project(gomagpiettscpp LANGUAGES C CXX)
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
+
+set(MAGPIE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/sources/magpie-tts.cpp)
+
+# Override upstream's CMAKE_CUDA_ARCHITECTURES before add_subdirectory.
+if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
+    set(CMAKE_CUDA_ARCHITECTURES "75-virtual;80-virtual;86-real;89-real")
+endif()
+
+# The magpie-tts C-API is exported directly by the upstream shared library
+# (magpie_tts_capi_* in libmagpie-tts.so, ggml statically linked inside), so
+# unlike qwen3-tts-cpp / moss-tts-cpp no local C shim is needed -- this wrapper
+# only configures the upstream project as a purego-loadable shared library.
+set(MAGPIE_SHARED       ON  CACHE BOOL "" FORCE)
+set(MAGPIE_BUILD_CLI    OFF CACHE BOOL "" FORCE)
+set(MAGPIE_BUILD_TESTS  OFF CACHE BOOL "" FORCE)
+
+# Upstream FORCE-overwrites GGML_CUDA / GGML_METAL / GGML_VULKAN / GGML_HIP from
+# its own MAGPIE_GGML_* toggles, which would silently discard the -DGGML_*=ON
+# flags the LocalAI Makefile passes for GPU BUILD_TYPEs. Translate them into the
+# MAGPIE_GGML_* vocabulary before add_subdirectory. (GGML_SYCL / GGML_BLAS and
+# the CPU ISA flags are not touched by upstream and reach ggml unchanged.)
+foreach(_be CUDA METAL VULKAN HIP)
+    if(GGML_${_be})
+        set(MAGPIE_GGML_${_be} ON CACHE BOOL "" FORCE)
+    endif()
+endforeach()
+
+add_subdirectory(${MAGPIE_DIR} magpie EXCLUDE_FROM_ALL)
+
+# Place libmagpie-tts.so at the build root, where the Makefile picks it up.
+set_target_properties(magpie-tts PROPERTIES LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})
--- a/backend/go/magpie-tts-cpp/Makefile
+++ b/backend/go/magpie-tts-cpp/Makefile
@@ -0,0 +1,140 @@
+CMAKE_ARGS?=
+BUILD_TYPE?=
+NATIVE?=false
+
+GOCMD?=go
+GO_TAGS?=
+JOBS?=$(shell nproc --ignore=1)
+
+# magpie-tts.cpp version
+MAGPIETTS_REPO?=https://github.com/mudler/magpie-tts.cpp
+MAGPIETTS_CPP_VERSION?=6f7696cffbfa1e85c17bc42eca24f5cbdb82c949
+SO_TARGET?=libgomagpiettscpp.so
+
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
+
+ifeq ($(NATIVE),false)
+	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+endif
+
+ifeq ($(BUILD_TYPE),cublas)
+	CMAKE_ARGS+=-DGGML_CUDA=ON
+else ifeq ($(BUILD_TYPE),openblas)
+	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else ifeq ($(BUILD_TYPE),clblas)
+	CMAKE_ARGS+=-DGGML_CLBLAST=ON -DCLBlast_DIR=/some/path
+else ifeq ($(BUILD_TYPE),hipblas)
+	# This ggml only understands GGML_HIP (GGML_HIPBLAS was removed upstream),
+	# so passing GGML_HIPBLAS silently produced a CPU-only build (see #10666).
+	ROCM_HOME ?= /opt/rocm
+	ROCM_PATH ?= /opt/rocm
+	export CXX=$(ROCM_HOME)/llvm/bin/clang++
+	export CC=$(ROCM_HOME)/llvm/bin/clang
+	AMDGPU_TARGETS ?= gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1151,gfx1200,gfx1201
+	CMAKE_ARGS+=-DGGML_HIP=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
+else ifeq ($(BUILD_TYPE),vulkan)
+	CMAKE_ARGS+=-DGGML_VULKAN=ON
+else ifeq ($(OS),Darwin)
+	ifneq ($(BUILD_TYPE),metal)
+		CMAKE_ARGS+=-DGGML_METAL=OFF
+	else
+		CMAKE_ARGS+=-DGGML_METAL=ON
+		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
+	endif
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f16)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DGGML_SYCL_F16=ON
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f32)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx
+endif
+
+sources/magpie-tts.cpp:
+	mkdir -p sources/magpie-tts.cpp
+	cd sources/magpie-tts.cpp && \
+	git init && \
+	git remote add origin $(MAGPIETTS_REPO) && \
+	git fetch origin && \
+	git checkout $(MAGPIETTS_CPP_VERSION) && \
+	git submodule update --init --recursive --depth 1 --single-branch
+
+# Detect OS
+UNAME_S := $(shell uname -s)
+
+# Only build CPU variants on Linux
+ifeq ($(UNAME_S),Linux)
+	VARIANT_TARGETS = libgomagpiettscpp-avx.so libgomagpiettscpp-avx2.so libgomagpiettscpp-avx512.so libgomagpiettscpp-fallback.so
+else
+	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
+	VARIANT_TARGETS = libgomagpiettscpp-fallback.dylib
+endif
+
+magpie-tts-cpp: main.go gomagpiettscpp.go $(VARIANT_TARGETS)
+	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o magpie-tts-cpp ./
+
+package: magpie-tts-cpp
+	bash package.sh
+
+build: package
+
+clean: purge
+	rm -rf libgomagpiettscpp*.so libgomagpiettscpp*.dylib package sources/magpie-tts.cpp magpie-tts-cpp
+
+purge:
+	rm -rf build*
+
+# Variants must build sequentially
+.NOTPARALLEL:
+
+# Build all variants (Linux only)
+ifeq ($(UNAME_S),Linux)
+libgomagpiettscpp-avx.so: sources/magpie-tts.cpp
+	$(info ${GREEN}I magpie-tts-cpp build info:avx${RESET})
+	SO_TARGET=libgomagpiettscpp-avx.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomagpiettscpp-custom
+	rm -rf build-libgomagpiettscpp-avx.so
+
+libgomagpiettscpp-avx2.so: sources/magpie-tts.cpp
+	$(info ${GREEN}I magpie-tts-cpp build info:avx2${RESET})
+	SO_TARGET=libgomagpiettscpp-avx2.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgomagpiettscpp-custom
+	rm -rf build-libgomagpiettscpp-avx2.so
+
+libgomagpiettscpp-avx512.so: sources/magpie-tts.cpp
+	$(info ${GREEN}I magpie-tts-cpp build info:avx512${RESET})
+	SO_TARGET=libgomagpiettscpp-avx512.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libgomagpiettscpp-custom
+	rm -rf build-libgomagpiettscpp-avx512.so
+endif
+
+# Build fallback variant (all platforms)
+libgomagpiettscpp-fallback.so: sources/magpie-tts.cpp
+	$(info ${GREEN}I magpie-tts-cpp build info:fallback${RESET})
+	SO_TARGET=libgomagpiettscpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomagpiettscpp-custom
+	rm -rf build-libgomagpiettscpp-fallback.so
+
+# Build fallback variant as a dylib (Darwin)
+libgomagpiettscpp-fallback.dylib: sources/magpie-tts.cpp
+	$(info ${GREEN}I magpie-tts-cpp build info:fallback (dylib)${RESET})
+	SO_TARGET=libgomagpiettscpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomagpiettscpp-custom
+	rm -rf build-libgomagpiettscpp-fallback.dylib
+
+libgomagpiettscpp-custom: CMakeLists.txt
+	mkdir -p build-$(SO_TARGET) && \
+	cd build-$(SO_TARGET) && \
+	cmake .. $(CMAKE_ARGS) && \
+	cmake --build . --config Release -j$(JOBS) --target magpie-tts && \
+	cd .. && \
+	(mv build-$(SO_TARGET)/libmagpie-tts.so ./$(SO_TARGET) 2>/dev/null || \
+	 mv build-$(SO_TARGET)/libmagpie-tts.dylib ./$(SO_TARGET) 2>/dev/null)
+
+test: magpie-tts-cpp
+	@echo "Running magpie-tts-cpp tests..."
+	bash test.sh
+	@echo "magpie-tts-cpp tests completed."
+
+all: magpie-tts-cpp package
--- a/backend/go/magpie-tts-cpp/README.md
+++ b/backend/go/magpie-tts-cpp/README.md
@@ -0,0 +1,69 @@
+# Magpie TTS C++ backend
+
+This backend runs NVIDIA's **Magpie TTS Multilingual 357M** GGUF through
+[magpie-tts.cpp](https://github.com/mudler/magpie-tts.cpp), a from-scratch
+C++/ggml port (model + NanoCodec + tokenizer + G2P dictionaries in one
+self-contained GGUF, no Python at inference time). It generates **22.05 kHz
+mono** speech in 5 baked voices across 9+ languages.
+
+The library is loaded via purego (cgo-less `dlopen`) exactly like
+`qwen3-tts-cpp` / `moss-tts-cpp`; the flat C-API (`magpie_tts_capi_*`) is
+exported directly by the upstream shared library, so there is no local C shim.
+
+## Model configuration
+
+The model path points at the single GGUF:
+
+```yaml
+name: magpie-tts-cpp
+backend: magpie-tts-cpp
+parameters:
+  model: magpie-tts-multilingual-357m-q8_0.gguf
+known_usecases:
+  - tts
+options:
+  - "speaker:Aria"   # optional default voice (Aria, Jason, John, Leo, Sofia, or 0-4)
+  - "language:en"    # optional default language
+```
+
+GGUFs live at
+[mudler/magpie-tts.cpp-gguf](https://huggingface.co/mudler/magpie-tts.cpp-gguf)
+(q8_0 recommended: near-lossless, ~624 MB, fastest decode).
+
+## Voices and languages
+
+Magpie has 5 baked speakers - `Aria`, `Jason`, `John`, `Leo`, `Sofia` - and no
+voice cloning. The request `voice` accepts the names case-insensitively or the
+indices `0`-`4`; empty selects Aria. Languages: `en`, `es`, `de`, `fr`, `it`,
+`pt-BR`, `hi`, `vi`, `ko`, `ar-AE`, `ar-SA`, `ar-MSA` (case-insensitive;
+default `en`).
+
+## API example
+
+```bash
+curl http://localhost:8080/v1/audio/speech \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "model": "magpie-tts-cpp",
+    "input": "Hello world, this is a test of the text to speech system.",
+    "voice": "sofia",
+    "language": "en"
+  }' \
+  --output speech.wav
+```
+
+## Native end-to-end test
+
+The labeled test loads a real GGUF, synthesizes WAVs (verifying rate, layout
+and non-silence), and exercises the streaming path:
+
+```bash
+make -C backend/go/magpie-tts-cpp magpie-tts-cpp
+
+MAGPIETTS_MODEL=/path/to/magpie-tts-multilingual-357m-q8_0.gguf \
+MAGPIETTS_LIBRARY=backend/go/magpie-tts-cpp/libgomagpiettscpp-fallback.so \
+  go test ./backend/go/magpie-tts-cpp -ginkgo.label-filter=e2e
+```
+
+`bash test.sh` does the same and auto-downloads the q8_0 GGUF when
+`MAGPIETTS_MODEL` is unset.
--- a/backend/go/magpie-tts-cpp/audio.go
+++ b/backend/go/magpie-tts-cpp/audio.go
@@ -0,0 +1,93 @@
+package main
+
+import (
+	"bytes"
+	"encoding/binary"
+	"fmt"
+	"os"
+
+	"github.com/go-audio/audio"
+	"github.com/go-audio/wav"
+)
+
+// magpieSampleRate is the fixed Magpie TTS Multilingual (NanoCodec) output
+// rate: 22.05 kHz.
+const magpieSampleRate = 22050
+
+// magpieChannels is the fixed output layout: mono.
+const magpieChannels = 1
+
+// wavHeaderMono returns a 44-byte WAV header for a streaming 16-bit mono PCM
+// stream at 22050 Hz, with placeholder (0xFFFFFFFF) sizes since the total
+// length is unknown up front. Emitted as the first chunk of TTSStream so the
+// HTTP layer receives a self-describing WAV.
+func wavHeaderMono() []byte {
+	const blockAlign = magpieChannels * 2 // 16-bit mono
+	var buf bytes.Buffer
+	w := func(v any) { _ = binary.Write(&buf, binary.LittleEndian, v) }
+	buf.WriteString("RIFF")
+	w(uint32(0xFFFFFFFF))
+	buf.WriteString("WAVE")
+	buf.WriteString("fmt ")
+	w(uint32(16))                            // Subchunk1Size
+	w(uint16(1))                             // PCM
+	w(uint16(magpieChannels))                // mono
+	w(uint32(magpieSampleRate))              // sample rate
+	w(uint32(magpieSampleRate * blockAlign)) // byte rate = SR * blockAlign
+	w(uint16(blockAlign))                    // block align
+	w(uint16(16))                            // bits per sample
+	buf.WriteString("data")
+	w(uint32(0xFFFFFFFF))
+	return buf.Bytes()
+}
+
+// floatToPCM16LE clamps each sample to [-1,1] and encodes it as little-endian
+// signed 16-bit PCM.
+func floatToPCM16LE(samples []float32) []byte {
+	out := make([]byte, len(samples)*2)
+	for i, s := range samples {
+		if s > 1 {
+			s = 1
+		} else if s < -1 {
+			s = -1
+		}
+		v := int16(s * 32767)
+		out[i*2] = byte(v)        // #nosec G115 -- intentional little-endian split of a clamped int16
+		out[i*2+1] = byte(v >> 8) // #nosec G115 -- high byte of the same clamped int16
+	}
+	return out
+}
+
+// writeWAVMono writes float samples as a finalized 16-bit mono WAV at
+// 22050 Hz.
+func writeWAVMono(dst string, samples []float32) error {
+	f, err := os.Create(dst) // #nosec G304 -- dst is the server-chosen output path from the TTS request, not user-traversable
+	if err != nil {
+		return fmt.Errorf("magpie-tts: create %q: %w", dst, err)
+	}
+	enc := wav.NewEncoder(f, magpieSampleRate, 16, magpieChannels, 1)
+	ints := make([]int, len(samples))
+	for i, s := range samples {
+		if s > 1 {
+			s = 1
+		} else if s < -1 {
+			s = -1
+		}
+		ints[i] = int(s * 32767)
+	}
+	b := &audio.IntBuffer{
+		Format:         &audio.Format{NumChannels: magpieChannels, SampleRate: magpieSampleRate},
+		Data:           ints,
+		SourceBitDepth: 16,
+	}
+	if err := enc.Write(b); err != nil {
+		_ = enc.Close()
+		_ = f.Close()
+		return fmt.Errorf("magpie-tts: encode WAV: %w", err)
+	}
+	if err := enc.Close(); err != nil {
+		_ = f.Close()
+		return fmt.Errorf("magpie-tts: finalize WAV: %w", err)
+	}
+	return f.Close()
+}
--- a/backend/go/magpie-tts-cpp/e2e_test.go
+++ b/backend/go/magpie-tts-cpp/e2e_test.go
@@ -0,0 +1,127 @@
+package main
+
+import (
+	"encoding/binary"
+	"math"
+	"os"
+
+	"github.com/ebitengine/purego"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func ttsReq(text, voice, lang, dst string) *pb.TTSRequest {
+	r := &pb.TTSRequest{Text: text, Voice: voice, Dst: dst}
+	if lang != "" {
+		r.Language = &lang
+	}
+	return r
+}
+
+// wavRMS parses a 16-bit PCM WAV file and returns (sampleRate, channels, RMS
+// of the normalized samples).
+func wavRMS(path string) (int, int, float64) {
+	data, err := os.ReadFile(path) // #nosec G304 -- test-owned temp file
+	Expect(err).ToNot(HaveOccurred())
+	Expect(len(data)).To(BeNumerically(">", 44))
+	Expect(string(data[0:4])).To(Equal("RIFF"))
+	Expect(string(data[8:12])).To(Equal("WAVE"))
+	channels := int(binary.LittleEndian.Uint16(data[22:24]))
+	rate := int(binary.LittleEndian.Uint32(data[24:28]))
+	// Find the data chunk (go-audio writes fmt first, data after).
+	off := 12
+	for off+8 <= len(data) {
+		id := string(data[off : off+4])
+		sz := int(binary.LittleEndian.Uint32(data[off+4 : off+8]))
+		if id == "data" {
+			pcm := data[off+8:]
+			if sz < len(pcm) {
+				pcm = pcm[:sz]
+			}
+			var sum float64
+			n := len(pcm) / 2
+			for i := 0; i < n; i++ {
+				s := float64(int16(binary.LittleEndian.Uint16(pcm[i*2:]))) / 32768.0
+				sum += s * s
+			}
+			Expect(n).To(BeNumerically(">", 0))
+			return rate, channels, math.Sqrt(sum / float64(n))
+		}
+		off += 8 + sz
+	}
+	Fail("no data chunk found in " + path)
+	return 0, 0, 0
+}
+
+var _ = Describe("magpie-tts-cpp e2e", Label("e2e"), func() {
+	var (
+		loaded  bool
+		backend *MagpieTtsCpp
+	)
+
+	BeforeEach(func() {
+		modelPath := os.Getenv("MAGPIETTS_MODEL")
+		if modelPath == "" {
+			Skip("MAGPIETTS_MODEL not set; skipping e2e")
+		}
+		if !loaded {
+			lib := os.Getenv("MAGPIETTS_LIBRARY")
+			if lib == "" {
+				lib = "./libgomagpiettscpp-fallback.so"
+			}
+			h, err := purego.Dlopen(lib, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+			Expect(err).ToNot(HaveOccurred())
+			purego.RegisterLibFunc(&CppAbiVersion, h, "magpie_tts_capi_abi_version")
+			purego.RegisterLibFunc(&CppLoad, h, "magpie_tts_capi_load")
+			purego.RegisterLibFunc(&CppFree, h, "magpie_tts_capi_free")
+			purego.RegisterLibFunc(&CppSynthesize, h, "magpie_tts_capi_synthesize")
+			purego.RegisterLibFunc(&CppFreeAudio, h, "magpie_tts_capi_free_audio")
+			purego.RegisterLibFunc(&CppLastError, h, "magpie_tts_capi_last_error")
+
+			backend = &MagpieTtsCpp{}
+			Expect(backend.Load(&pb.ModelOptions{ModelFile: modelPath})).To(Succeed())
+			loaded = true
+		}
+	})
+
+	It("synthesizes a non-silent 22.05 kHz mono WAV via TTS", func() {
+		dst := GinkgoT().TempDir() + "/out.wav"
+		Expect(backend.TTS(ttsReq("Hello world, this is a test.", "Aria", "en", dst))).To(Succeed())
+		rate, channels, rms := wavRMS(dst)
+		Expect(rate).To(Equal(22050))
+		Expect(channels).To(Equal(1))
+		Expect(rms).To(BeNumerically(">", 0.01), "audio should not be silent")
+	})
+
+	It("accepts a case-insensitive voice and a speaker index", func() {
+		dst := GinkgoT().TempDir() + "/out.wav"
+		Expect(backend.TTS(ttsReq("Short test.", "sofia", "en", dst))).To(Succeed())
+		Expect(backend.TTS(ttsReq("Short test.", "1", "en", dst))).To(Succeed())
+	})
+
+	It("rejects an unknown voice before reaching the engine", func() {
+		dst := GinkgoT().TempDir() + "/out.wav"
+		err := backend.TTS(ttsReq("Short test.", "not-a-speaker", "en", dst))
+		Expect(err).To(MatchError(ContainSubstring("unknown voice")))
+	})
+
+	It("streams a self-describing WAV via TTSStream", func() {
+		results := make(chan []byte, 4096)
+		done := make(chan error, 1)
+		go func() { done <- backend.TTSStream(ttsReq("Hello there, streaming test.", "", "", ""), results) }()
+
+		var chunks int
+		var first []byte
+		for c := range results {
+			if chunks == 0 {
+				first = c
+			}
+			chunks++
+		}
+		Expect(<-done).ToNot(HaveOccurred())
+		Expect(chunks).To(BeNumerically(">=", 2))
+		Expect(string(first[0:4])).To(Equal("RIFF"))
+		Expect(string(first[8:12])).To(Equal("WAVE"))
+	})
+})
--- a/backend/go/magpie-tts-cpp/gomagpiettscpp.go
+++ b/backend/go/magpie-tts-cpp/gomagpiettscpp.go
@@ -0,0 +1,147 @@
+package main
+
+import (
+	"fmt"
+	"path/filepath"
+	"unsafe"
+
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/mudler/xlog"
+)
+
+// capiABIVersion is the magpie_tts_capi.h surface this backend binds. Bumped
+// upstream on any breaking signature/semantics change; refuse to run on a
+// mismatch instead of crashing inside a miscompiled call.
+const capiABIVersion = 1
+
+var (
+	// magpie_tts_capi_abi_version() int
+	CppAbiVersion func() int
+	// magpie_tts_capi_load(gguf_path) -> ctx (NULL on failure)
+	CppLoad func(path string) uintptr
+	// magpie_tts_capi_free(ctx)
+	CppFree func(ctx uintptr)
+	// magpie_tts_capi_synthesize(ctx, text, language, speaker, out_n) -> float*
+	// 22050 Hz mono f32 PCM in [-1,1]; NULL on failure (see last_error).
+	CppSynthesize func(ctx uintptr, text, language, speaker string, outN unsafe.Pointer) uintptr
+	// magpie_tts_capi_free_audio(ptr)
+	CppFreeAudio func(ptr uintptr)
+	// magpie_tts_capi_last_error(ctx) -> const char* (ctx-owned, "" if none)
+	CppLastError func(ctx uintptr) string
+)
+
+// MagpieTtsCpp serves the Magpie TTS Multilingual 357M GGUF through the
+// magpie-tts.cpp C-API. The context is stateful (per-call error buffer, reused
+// graph allocator) and NOT safe for concurrent synthesize calls, so
+// base.SingleThread serializes everything behind the server-level lock.
+type MagpieTtsCpp struct {
+	base.SingleThread
+	ctx  uintptr
+	opts loadOptions
+}
+
+func (m *MagpieTtsCpp) Load(opts *pb.ModelOptions) error {
+	model := opts.ModelFile
+	if model == "" {
+		model = opts.ModelPath
+	}
+	if !filepath.IsAbs(model) && opts.ModelPath != "" {
+		model = filepath.Join(opts.ModelPath, model)
+	}
+
+	m.opts = parseOptions(opts.Options)
+
+	if abi := CppAbiVersion(); abi != capiABIVersion {
+		return fmt.Errorf("magpie-tts: C-API ABI mismatch: library reports v%d, backend built for v%d", abi, capiABIVersion)
+	}
+
+	xlog.Info("[magpie-tts-cpp] Load", "model", model)
+
+	ctx := CppLoad(model)
+	if ctx == 0 {
+		// Load failures have no context to query last_error on; the C side
+		// logs the reason to stderr.
+		return fmt.Errorf("magpie-tts: failed to load model %q", model)
+	}
+	m.ctx = ctx
+	return nil
+}
+
+// lastError surfaces the context's last error, falling back to a generic
+// message when the C side left it empty.
+func (m *MagpieTtsCpp) lastError() string {
+	if m.ctx == 0 {
+		return "no model loaded"
+	}
+	if e := CppLastError(m.ctx); e != "" {
+		return e
+	}
+	return "unknown error"
+}
+
+// synthesize runs one C-API synthesis and copies the PCM out of C memory.
+func (m *MagpieTtsCpp) synthesize(req *pb.TTSRequest) ([]float32, error) {
+	if m.ctx == 0 {
+		return nil, fmt.Errorf("magpie-tts: no model loaded")
+	}
+	if req.Text == "" {
+		return nil, fmt.Errorf("magpie-tts: TTS requires text")
+	}
+	speaker, err := resolveSpeaker(req.Voice, m.opts.speaker)
+	if err != nil {
+		return nil, err
+	}
+	lang := resolveLanguage(req.Language, m.opts.language)
+
+	var n int32
+	ptr := CppSynthesize(m.ctx, req.Text, lang, speaker, unsafe.Pointer(&n)) // #nosec G103 -- out-param for the purego-bound C-API
+	if ptr == 0 {
+		return nil, fmt.Errorf("magpie-tts: synthesis failed: %s", m.lastError())
+	}
+	// Register the free as soon as we own a non-null buffer, so the n<=0 guard
+	// below cannot leak it (defensive: the C contract returns NULL on failure).
+	defer CppFreeAudio(ptr)
+	if n <= 0 {
+		return nil, fmt.Errorf("magpie-tts: synthesis produced no samples")
+	}
+	//nolint:govet // C-allocated PCM, copied out before free
+	src := unsafe.Slice((*float32)(unsafe.Pointer(ptr)), int(n)) // #nosec G103 -- C-allocated PCM, copied out before free
+	out := make([]float32, int(n))
+	copy(out, src)
+	return out, nil
+}
+
+func (m *MagpieTtsCpp) TTS(req *pb.TTSRequest) error {
+	if req.Dst == "" {
+		return fmt.Errorf("magpie-tts: TTS requires a destination path")
+	}
+	samples, err := m.synthesize(req)
+	if err != nil {
+		return err
+	}
+	return writeWAVMono(req.Dst, samples)
+}
+
+// TTSStream synthesizes one-shot (the magpie C-API has no streaming call) and
+// then emits a self-describing mono WAV: a header chunk followed by the PCM in
+// fixed-size slices, so the HTTP layer still receives a streamed WAV (the gRPC
+// TTSStream path never sets Message, so the backend owns the header - see
+// core/backend/tts.go:ModelTTSStream).
+func (m *MagpieTtsCpp) TTSStream(req *pb.TTSRequest, results chan []byte) error {
+	defer close(results)
+	samples, err := m.synthesize(req)
+	if err != nil {
+		return err
+	}
+	results <- wavHeaderMono()
+	const sampleChunk = 4096 // mono samples per emitted chunk
+	for off := 0; off < len(samples); off += sampleChunk {
+		end := off + sampleChunk
+		if end > len(samples) {
+			end = len(samples)
+		}
+		results <- floatToPCM16LE(samples[off:end])
+	}
+	return nil
+}
--- a/backend/go/magpie-tts-cpp/magpiettscpp_test.go
+++ b/backend/go/magpie-tts-cpp/magpiettscpp_test.go
@@ -0,0 +1,115 @@
+package main
+
+import (
+	"testing"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func TestMagpieTtsCpp(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "magpie-tts-cpp suite")
+}
+
+var _ = Describe("resolveSpeaker", func() {
+	It("canonicalizes case-insensitive names", func() {
+		for in, want := range map[string]string{
+			"aria": "Aria", "JASON": "Jason", "john": "John",
+			"Leo": "Leo", "sofia": "Sofia",
+		} {
+			got, err := resolveSpeaker(in, "")
+			Expect(err).ToNot(HaveOccurred())
+			Expect(got).To(Equal(want))
+		}
+	})
+	It("accepts indices 0-4", func() {
+		for in, want := range map[string]string{
+			"0": "Aria", "1": "Jason", "2": "John", "3": "Leo", "4": "Sofia",
+		} {
+			got, err := resolveSpeaker(in, "")
+			Expect(err).ToNot(HaveOccurred())
+			Expect(got).To(Equal(want))
+		}
+	})
+	It("selects the engine default on empty", func() {
+		got, err := resolveSpeaker("", "")
+		Expect(err).ToNot(HaveOccurred())
+		Expect(got).To(BeEmpty())
+	})
+	It("falls back to the model-level default speaker", func() {
+		got, err := resolveSpeaker("", "sofia")
+		Expect(err).ToNot(HaveOccurred())
+		Expect(got).To(Equal("Sofia"))
+	})
+	It("prefers the request voice over the fallback", func() {
+		got, err := resolveSpeaker("leo", "sofia")
+		Expect(err).ToNot(HaveOccurred())
+		Expect(got).To(Equal("Leo"))
+	})
+	It("rejects out-of-range indices", func() {
+		_, err := resolveSpeaker("5", "")
+		Expect(err).To(HaveOccurred())
+		_, err = resolveSpeaker("-1", "")
+		Expect(err).To(HaveOccurred())
+	})
+	It("rejects unknown names with the valid choices", func() {
+		_, err := resolveSpeaker("serena", "")
+		Expect(err).To(MatchError(ContainSubstring("Aria, Jason, John, Leo, Sofia")))
+	})
+})
+
+var _ = Describe("resolveLanguage", func() {
+	strp := func(s string) *string { return &s }
+
+	It("defaults to empty (engine picks en)", func() {
+		Expect(resolveLanguage(nil, "")).To(BeEmpty())
+	})
+	It("canonicalizes case for known codes", func() {
+		Expect(resolveLanguage(strp("EN"), "")).To(Equal("en"))
+		Expect(resolveLanguage(strp("pt-br"), "")).To(Equal("pt-BR"))
+		Expect(resolveLanguage(strp("AR-MSA"), "")).To(Equal("ar-MSA"))
+	})
+	It("falls back to the model-level default language", func() {
+		Expect(resolveLanguage(nil, "de")).To(Equal("de"))
+		Expect(resolveLanguage(strp(""), "PT-BR")).To(Equal("pt-BR"))
+	})
+	It("prefers the request language over the fallback", func() {
+		Expect(resolveLanguage(strp("it"), "de")).To(Equal("it"))
+	})
+	It("passes unknown codes through verbatim", func() {
+		Expect(resolveLanguage(strp("zh"), "")).To(Equal("zh"))
+	})
+})
+
+var _ = Describe("parseOptions", func() {
+	It("reads speaker and language defaults", func() {
+		o := parseOptions([]string{"speaker:Jason", "language:de"})
+		Expect(o.speaker).To(Equal("Jason"))
+		Expect(o.language).To(Equal("de"))
+	})
+	It("accepts the voice/lang aliases and ignores unknown keys", func() {
+		o := parseOptions([]string{"voice: sofia ", "lang: pt-BR", "bogus:1", "novalue"})
+		Expect(o.speaker).To(Equal("sofia"))
+		Expect(o.language).To(Equal("pt-BR"))
+	})
+})
+
+var _ = Describe("audio encoding", func() {
+	It("emits a well-formed streaming mono WAV header", func() {
+		h := wavHeaderMono()
+		Expect(h).To(HaveLen(44))
+		Expect(string(h[0:4])).To(Equal("RIFF"))
+		Expect(string(h[8:12])).To(Equal("WAVE"))
+		// channels (offset 22) == 1, sample rate (offset 24) == 22050
+		Expect(int(h[22]) | int(h[23])<<8).To(Equal(1))
+		Expect(int(h[24]) | int(h[25])<<8 | int(h[26])<<16 | int(h[27])<<24).To(Equal(22050))
+	})
+	It("clamps float PCM to int16", func() {
+		b := floatToPCM16LE([]float32{2, -2, 0})
+		Expect(b).To(HaveLen(6))
+		Expect(int16(uint16(b[0]) | uint16(b[1])<<8)).To(Equal(int16(32767)))
+		Expect(int16(uint16(b[2]) | uint16(b[3])<<8)).To(Equal(int16(-32767)))
+		Expect(int16(uint16(b[4]) | uint16(b[5])<<8)).To(Equal(int16(0)))
+	})
+})
--- a/backend/go/magpie-tts-cpp/main.go
+++ b/backend/go/magpie-tts-cpp/main.go
@@ -0,0 +1,54 @@
+package main
+
+// Note: this is started internally by LocalAI and a server is allocated for each model
+import (
+	"flag"
+	"os"
+	"runtime"
+
+	"github.com/ebitengine/purego"
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+type LibFuncs struct {
+	FuncPtr any
+	Name    string
+}
+
+func main() {
+	libName := os.Getenv("MAGPIETTS_LIBRARY")
+	if libName == "" {
+		if runtime.GOOS == "darwin" {
+			libName = "./libgomagpiettscpp-fallback.dylib"
+		} else {
+			libName = "./libgomagpiettscpp-fallback.so"
+		}
+	}
+
+	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	if err != nil {
+		panic(err)
+	}
+
+	libFuncs := []LibFuncs{
+		{&CppAbiVersion, "magpie_tts_capi_abi_version"},
+		{&CppLoad, "magpie_tts_capi_load"},
+		{&CppFree, "magpie_tts_capi_free"},
+		{&CppSynthesize, "magpie_tts_capi_synthesize"},
+		{&CppFreeAudio, "magpie_tts_capi_free_audio"},
+		{&CppLastError, "magpie_tts_capi_last_error"},
+	}
+	for _, lf := range libFuncs {
+		purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
+	}
+
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &MagpieTtsCpp{}); err != nil {
+		panic(err)
+	}
+}
--- a/backend/go/magpie-tts-cpp/options.go
+++ b/backend/go/magpie-tts-cpp/options.go
@@ -0,0 +1,108 @@
+package main
+
+import (
+	"fmt"
+	"strconv"
+	"strings"
+)
+
+// loadOptions holds the parsed model-level options. Magpie is a single
+// self-contained GGUF (model + codec + tokenizer + G2P dictionaries), so the
+// options only cover synthesis defaults.
+type loadOptions struct {
+	// speaker is the default baked speaker when a request has no voice.
+	speaker string
+	// language is the default language when a request has none ("" = engine
+	// default, which is "en").
+	language string
+}
+
+func splitOption(o string) (key, value string, ok bool) {
+	i := strings.Index(o, ":")
+	if i < 0 {
+		return "", "", false
+	}
+	return strings.TrimSpace(o[:i]), strings.TrimSpace(o[i+1:]), true
+}
+
+// parseOptions reads the backend "key:value" option slice. Unknown keys are
+// ignored.
+func parseOptions(opts []string) loadOptions {
+	var o loadOptions
+	for _, oo := range opts {
+		key, value, ok := splitOption(oo)
+		if !ok {
+			continue
+		}
+		switch key {
+		case "speaker", "voice":
+			o.speaker = value
+		case "language", "lang":
+			o.language = value
+		}
+	}
+	return o
+}
+
+// magpieSpeakers are the baked speakers of Magpie TTS Multilingual 357M, in
+// index order (the engine matches names exactly, so the Go side canonicalizes
+// case-insensitive names and 0-4 indices to these strings).
+var magpieSpeakers = []string{"Aria", "Jason", "John", "Leo", "Sofia"}
+
+// resolveSpeaker maps the request voice (falling back to the model-level
+// default) onto a canonical baked speaker name. Accepted forms:
+// case-insensitive names (aria, JASON, ...) and indices 0-4. Empty selects the
+// engine default (speaker 0, Aria). Anything else is rejected with the valid
+// choices, instead of surfacing the engine's late error.
+func resolveSpeaker(voice, fallback string) (string, error) {
+	v := strings.TrimSpace(voice)
+	if v == "" {
+		v = strings.TrimSpace(fallback)
+	}
+	if v == "" {
+		return "", nil
+	}
+	if idx, err := strconv.Atoi(v); err == nil {
+		if idx < 0 || idx >= len(magpieSpeakers) {
+			return "", fmt.Errorf("magpie-tts: speaker index %d out of range 0-%d", idx, len(magpieSpeakers)-1)
+		}
+		return magpieSpeakers[idx], nil
+	}
+	for _, s := range magpieSpeakers {
+		if strings.EqualFold(s, v) {
+			return s, nil
+		}
+	}
+	return "", fmt.Errorf("magpie-tts: unknown voice %q (valid: %s, or 0-%d)",
+		voice, strings.Join(magpieSpeakers, ", "), len(magpieSpeakers)-1)
+}
+
+// magpieLanguages are the canonical language codes the tokenizer's language
+// map knows (exact-match on the C side), keyed by their lowercase form so
+// requests can be case-insensitive.
+var magpieLanguages = map[string]string{
+	"en": "en", "es": "es", "de": "de", "fr": "fr", "it": "it",
+	"pt-br": "pt-BR", "hi": "hi", "vi": "vi", "ko": "ko",
+	"ar-ae": "ar-AE", "ar-sa": "ar-SA", "ar-msa": "ar-MSA",
+}
+
+// resolveLanguage picks the request language, else the model-level default,
+// else "" (the engine defaults to "en"), canonicalizing case for the known
+// codes. Unknown codes pass through verbatim so the engine reports them with
+// its own exact-vocabulary error.
+func resolveLanguage(reqLang *string, fallback string) string {
+	l := ""
+	if reqLang != nil {
+		l = strings.TrimSpace(*reqLang)
+	}
+	if l == "" {
+		l = strings.TrimSpace(fallback)
+	}
+	if l == "" {
+		return ""
+	}
+	if canon, ok := magpieLanguages[strings.ToLower(l)]; ok {
+		return canon
+	}
+	return l
+}
--- a/backend/go/magpie-tts-cpp/package.sh
+++ b/backend/go/magpie-tts-cpp/package.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+
+# Script to copy the appropriate libraries based on architecture
+# This script is used in the final stage of the Dockerfile
+
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
+
+# Create lib directory
+mkdir -p $CURDIR/package/lib
+
+cp -avf $CURDIR/magpie-tts-cpp $CURDIR/package/
+cp -fv $CURDIR/libgomagpiettscpp-*.so $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgomagpiettscpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/run.sh $CURDIR/package/
+
+# Detect architecture and copy appropriate libraries
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    # x86_64 architecture
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    # ARM64 architecture
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ $(uname -s) = "Darwin" ]; then
+    echo "Detected Darwin"
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+# Package GPU libraries based on BUILD_TYPE
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah $CURDIR/package/
+ls -liah $CURDIR/package/lib/
--- a/backend/go/magpie-tts-cpp/run.sh
+++ b/backend/go/magpie-tts-cpp/run.sh
@@ -0,0 +1,57 @@
+#!/bin/bash
+set -ex
+
+# Get the absolute current dir where the script is located
+CURDIR=$(dirname "$(realpath "$0")")
+
+cd /
+
+echo "CPU info:"
+if [ "$(uname)" != "Darwin" ]; then
+	grep -e "model\sname" /proc/cpuinfo | head -1
+	grep -e "flags" /proc/cpuinfo | head -1
+fi
+
+if [ "$(uname)" = "Darwin" ]; then
+	# macOS: single dylib variant (Metal or Accelerate)
+	LIBRARY="$CURDIR/libgomagpiettscpp-fallback.dylib"
+	export DYLD_LIBRARY_PATH="$CURDIR"/lib:$DYLD_LIBRARY_PATH
+else
+	LIBRARY="$CURDIR/libgomagpiettscpp-fallback.so"
+
+	if grep -q -e "\savx\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX    found OK"
+		if [ -e "$CURDIR"/libgomagpiettscpp-avx.so ]; then
+			LIBRARY="$CURDIR/libgomagpiettscpp-avx.so"
+		fi
+	fi
+
+	if grep -q -e "\savx2\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX2   found OK"
+		if [ -e "$CURDIR"/libgomagpiettscpp-avx2.so ]; then
+			LIBRARY="$CURDIR/libgomagpiettscpp-avx2.so"
+		fi
+	fi
+
+	# Check avx 512
+	if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX512F found OK"
+		if [ -e "$CURDIR"/libgomagpiettscpp-avx512.so ]; then
+			LIBRARY="$CURDIR/libgomagpiettscpp-avx512.so"
+		fi
+	fi
+
+	export LD_LIBRARY_PATH="$CURDIR"/lib:$LD_LIBRARY_PATH
+fi
+
+export MAGPIETTS_LIBRARY=$LIBRARY
+
+# If there is a lib/ld.so, use it
+if [ -f "$CURDIR"/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	echo "Using library: $LIBRARY"
+	exec "$CURDIR"/lib/ld.so "$CURDIR"/magpie-tts-cpp "$@"
+fi
+
+echo "Using library: $LIBRARY"
+exec "$CURDIR"/magpie-tts-cpp "$@"
--- a/backend/go/magpie-tts-cpp/test.sh
+++ b/backend/go/magpie-tts-cpp/test.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+cd "$CURDIR"
+
+echo "Running magpie-tts-cpp backend tests..."
+
+# Auto-download the q8_0 GGUF only when MAGPIETTS_MODEL is not set.
+if [ -z "$MAGPIETTS_MODEL" ]; then
+    MODEL_DIR="./magpie-tts-models"
+    mkdir -p "$MODEL_DIR"
+    REPO_ID="mudler/magpie-tts.cpp-gguf"
+    BASE_URL="https://huggingface.co/${REPO_ID}/resolve/main"
+    FILE="magpie-tts-multilingual-357m-q8_0.gguf"
+    dest="${MODEL_DIR}/${FILE}"
+    if [ -f "${dest}" ]; then
+        echo "  [skip] ${FILE}"
+    else
+        echo "  [download] ${FILE}..."
+        curl -L -o "${dest}" "${BASE_URL}/${FILE}" --progress-bar
+    fi
+    export MAGPIETTS_MODEL="${dest}"
+fi
+
+go test -v -timeout 1200s .
+
+echo "All magpie-tts-cpp tests passed."
--- a/backend/index.yaml
+++ b/backend/index.yaml
@@ -1171,6 +1171,48 @@
    nvidia-l4t: "nvidia-l4t-arm64-moss-tts-cpp-development"
    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-moss-tts-cpp-development"
    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-moss-tts-cpp-development"
+- &magpiettscpp
+  name: "magpie-tts-cpp"
+  description: |
+    Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++
+    text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder +
+    autoregressive decoder over NanoCodec tokens), running from a single
+    self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no
+    Python at inference time. 22.05kHz mono output, 5 baked voices (Aria,
+    Jason, John, Leo, Sofia), 9+ languages.
+  urls:
+    - https://github.com/mudler/magpie-tts.cpp
+    - https://huggingface.co/mudler/magpie-tts.cpp-gguf
+  tags:
+    - text-to-speech
+    - tts
+  alias: "magpie-tts-cpp"
+  capabilities:
+    default: "cpu-magpie-tts-cpp"
+    nvidia: "cuda12-magpie-tts-cpp"
+    nvidia-cuda-13: "cuda13-magpie-tts-cpp"
+    nvidia-cuda-12: "cuda12-magpie-tts-cpp"
+    intel: "intel-sycl-f16-magpie-tts-cpp"
+    metal: "metal-magpie-tts-cpp"
+    amd: "rocm-magpie-tts-cpp"
+    vulkan: "vulkan-magpie-tts-cpp"
+    nvidia-l4t: "nvidia-l4t-arm64-magpie-tts-cpp"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-magpie-tts-cpp"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-magpie-tts-cpp"
+- !!merge <<: *magpiettscpp
+  name: "magpie-tts-cpp-development"
+  capabilities:
+    default: "cpu-magpie-tts-cpp-development"
+    nvidia: "cuda12-magpie-tts-cpp-development"
+    nvidia-cuda-13: "cuda13-magpie-tts-cpp-development"
+    nvidia-cuda-12: "cuda12-magpie-tts-cpp-development"
+    intel: "intel-sycl-f16-magpie-tts-cpp-development"
+    metal: "metal-magpie-tts-cpp-development"
+    amd: "rocm-magpie-tts-cpp-development"
+    vulkan: "vulkan-magpie-tts-cpp-development"
+    nvidia-l4t: "nvidia-l4t-arm64-magpie-tts-cpp-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-magpie-tts-cpp-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-magpie-tts-cpp-development"
 - &omnivoicecpp
  name: "omnivoice-cpp"
  description: |
@@ -4754,6 +4796,107 @@
  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-moss-tts-cpp"
  mirrors:
    - localai/localai-backends:master-gpu-nvidia-cuda-13-moss-tts-cpp
+## magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "nvidia-l4t-arm64-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-arm64-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "nvidia-l4t-arm64-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-arm64-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cuda13-nvidia-l4t-arm64-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cuda13-nvidia-l4t-arm64-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cpu-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-cpu-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "metal-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-metal-darwin-arm64-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "metal-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-metal-darwin-arm64-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cpu-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-cpu-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cuda12-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "rocm-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-rocm-hipblas-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "intel-sycl-f32-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f32-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "intel-sycl-f16-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f16-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "vulkan-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "vulkan-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cuda12-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "rocm-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-rocm-hipblas-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "intel-sycl-f32-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f32-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "intel-sycl-f16-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f16-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cuda13-magpie-tts-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-magpie-tts-cpp
+- !!merge <<: *magpiettscpp
+  name: "cuda13-magpie-tts-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-magpie-tts-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-magpie-tts-cpp
 ## omnivoice-cpp
 - !!merge <<: *omnivoicecpp
  name: "omnivoice-cpp-development"
--- a/core/config/backend_capabilities.go
+++ b/core/config/backend_capabilities.go
@@ -466,6 +466,12 @@ var BackendCapabilities = map[string]BackendCapability{
 		VoiceCloning:     referenceVoiceCloning(),
 		Description:      "Qwen3 TTS C++ - text-to-speech with streaming, named speakers, voice design and cloning (qwentts.cpp / GGML)",
 	},
+	"magpie-tts-cpp": {
+		GRPCMethods:      []GRPCMethod{MethodTTS, MethodTTSStream},
+		PossibleUsecases: []string{UsecaseTTS},
+		DefaultUsecases:  []string{UsecaseTTS},
+		Description:      "Magpie TTS C++ - NVIDIA Magpie TTS Multilingual 357M with 5 baked voices and 9+ languages (magpie-tts.cpp / GGML)",
+	},
 	"faster-qwen3-tts": {
 		GRPCMethods:      []GRPCMethod{MethodTTS},
 		PossibleUsecases: []string{UsecaseTTS},
--- a/core/http/endpoints/localai/backend.go
+++ b/core/http/endpoints/localai/backend.go
@@ -41,6 +41,7 @@ var knownPrefOnlyBackends = []schema.KnownBackend{
 	{Name: "kokoros", Modality: "tts", AutoDetect: false, Description: "Kokoros TTS (preference-only)"},
 	{Name: "qwen-tts", Modality: "tts", AutoDetect: false, Description: "Qwen TTS (preference-only)"},
 	{Name: "qwen3-tts-cpp", Modality: "tts", AutoDetect: false, Description: "Qwen3 TTS C++ (preference-only)"},
+	{Name: "magpie-tts-cpp", Modality: "tts", AutoDetect: false, Description: "Magpie TTS Multilingual C++ (preference-only)"},
 	{Name: "omnivoice-cpp", Modality: "tts", AutoDetect: false, Description: "OmniVoice C++ TTS with voice cloning and voice design (preference-only)"},
 	{Name: "faster-qwen3-tts", Modality: "tts", AutoDetect: false, Description: "Faster Qwen3 TTS (preference-only)"},
 	{Name: "supertonic", Modality: "tts", AutoDetect: false, Description: "Supertonic multilingual ONNX TTS (preference-only)"},
--- a/core/http/endpoints/localai/backend_test.go
+++ b/core/http/endpoints/localai/backend_test.go
@@ -157,6 +157,7 @@ var _ = Describe("Backend Endpoints", func() {
 			expectPrefOnly("kokoros", "tts")
 			expectPrefOnly("qwen-tts", "tts")
 			expectPrefOnly("qwen3-tts-cpp", "tts")
+			expectPrefOnly("magpie-tts-cpp", "tts")
 			expectPrefOnly("faster-qwen3-tts", "tts")
 			expectPrefOnly("supertonic", "tts")
 			expectPrefOnly("sam3-cpp", "detection")
--- a/docs/content/reference/compatibility-table.md
+++ b/docs/content/reference/compatibility-table.md
@@ -60,6 +60,7 @@ All backends listed here can be installed on demand from the [Backend Gallery]({
 | [VibeVoice](https://github.com/microsoft/VibeVoice) | Real-time TTS with voice cloning | CPU, CUDA 12/13, ROCm, Intel SYCL, Metal, Jetson L4T |
 | [vibevoice.cpp](https://github.com/mudler/vibevoice.cpp) | Native C++/GGML port of VibeVoice for TTS (voice cloning) and long-form ASR with diarization | CPU, CUDA 12/13, ROCm, Intel SYCL, Vulkan, Metal, Jetson L4T |
 | [moss-tts.cpp](https://github.com/mudler/moss-tts.cpp) | Native C++/GGML port of OpenMOSS MOSS-TTS-Local v1.5: 48 kHz stereo TTS with reference-audio voice cloning | CPU, CUDA 12/13, ROCm, Intel SYCL, Vulkan, Metal, Jetson L4T |
+| [magpie-tts.cpp](https://github.com/mudler/magpie-tts.cpp) | Native C++/GGML port of NVIDIA Magpie TTS Multilingual 357M: 22.05 kHz mono TTS, 5 baked voices, 9+ languages | CPU, CUDA 12/13, ROCm, Intel SYCL, Vulkan, Metal, Jetson L4T |
 | [Qwen3-TTS](https://github.com/QwenLM/Qwen3-TTS) | TTS with custom voice, voice design, and voice cloning | CPU, CUDA 12/13, ROCm, Intel SYCL, Metal, Jetson L4T |
 | [qwentts.cpp](https://github.com/ServeurpersoCom/qwentts.cpp) | Native C++/GGML Qwen3-TTS with streaming, named speakers, and voice design | CPU, CUDA 12/13, ROCm, Intel SYCL, Vulkan, Metal, Jetson L4T |
 | [OmniVoice](https://github.com/ServeurpersoCom/omnivoice.cpp) | Native C++/GGML TTS with voice cloning, voice design, and streaming | CPU, CUDA 12/13, ROCm, Intel SYCL, Vulkan, Metal, Jetson L4T |
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -6699,6 +6699,60 @@
    - filename: moss-tts-cpp-v1_5-f16/moss-tokenizer-v1_5.gguf
      sha256: d0f4f371f80ff32ba222b1b39c192df8285c7b88986a55f954454db69618479e
      uri: huggingface://mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF/moss-tokenizer-v1_5.gguf
+- &magpiettscpp_gallery
+  name: magpie-tts-cpp-357m-q8_0
+  variants:
+    - model: magpie-tts-cpp-357m-f16
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/mudler/magpie-tts.cpp-gguf
+    - https://github.com/mudler/magpie-tts.cpp
+    - https://huggingface.co/nvidia/magpie_tts_multilingual_357m
+  description: |
+    Magpie TTS Multilingual 357M (C++/ggml, magpie-tts.cpp), Q8_0 (~624 MB), near-lossless
+    and the fastest decode. Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual
+    (encoder + autoregressive decoder over NanoCodec tokens) from one self-contained GGUF
+    (model, codec, tokenizer, G2P dictionaries). 22.05kHz mono, 5 baked voices (set `voice`
+    to Aria, Jason, John, Leo, Sofia or 0-4), 9+ languages (en, es, de, fr, it, pt-BR, hi,
+    vi, ko, plus Arabic variants). Parity-gated per component against the NeMo reference.
+  license: other
+  tags:
+    - magpie-tts
+    - magpie-tts-cpp
+    - tts
+    - text-to-speech
+    - multilingual
+    - gguf
+    - ggml
+  last_checked: "2026-07-24"
+  overrides:
+    backend: magpie-tts-cpp
+    known_usecases:
+      - tts
+    name: magpie-tts-cpp-357m-q8_0
+    parameters:
+      model: magpie-tts-cpp-357m-q8_0/magpie-tts-multilingual-357m-q8_0.gguf
+  files:
+    - filename: magpie-tts-cpp-357m-q8_0/magpie-tts-multilingual-357m-q8_0.gguf
+      sha256: 0f26f552c82b45a176bd7b7de261581821d5e81acc99cedb4450fd20a10ad259
+      uri: huggingface://mudler/magpie-tts.cpp-gguf/magpie-tts-multilingual-357m-q8_0.gguf
+- !!merge <<: *magpiettscpp_gallery
+  name: magpie-tts-cpp-357m-f16
+  variants: []
+  description: |
+    Magpie TTS Multilingual 357M (C++/ggml, magpie-tts.cpp), F16 (~784 MB). 22.05kHz mono
+    text-to-speech with 5 baked voices and 9+ languages.
+  overrides:
+    backend: magpie-tts-cpp
+    known_usecases:
+      - tts
+    name: magpie-tts-cpp-357m-f16
+    parameters:
+      model: magpie-tts-cpp-357m-f16/magpie-tts-multilingual-357m-f16.gguf
+  files:
+    - filename: magpie-tts-cpp-357m-f16/magpie-tts-multilingual-357m-f16.gguf
+      sha256: cf1782f26703cac58b97ed453e42320e974a13be7b592f83be14e58f955b97ec
+      uri: huggingface://mudler/magpie-tts.cpp-gguf/magpie-tts-multilingual-357m-f16.gguf
 - name: omnivoice-cpp
  variants:
    - model: omnivoice-cpp-hq
--- a/scripts/lib/backend-filter.mjs
+++ b/scripts/lib/backend-filter.mjs
@@ -42,6 +42,14 @@ export function inferBackendPath(item) {
  if (item.backend === "moss-tts-cpp") {
    return `backend/go/moss-tts-cpp/`;
  }
+  // magpie-tts-cpp is a Go backend (Dockerfile.golang) wrapping the
+  // magpie-tts.cpp ggml port via purego, living in backend/go/magpie-tts-cpp/.
+  // Same explicit-branch rationale as its siblings above: the generic golang
+  // fallthrough would also resolve it, but this documents the mapping and
+  // guards a future dockerfile-suffix change.
+  if (item.backend === "magpie-tts-cpp") {
+    return `backend/go/magpie-tts-cpp/`;
+  }
  if (item.dockerfile.endsWith("golang")) {
    return `backend/go/${item.backend}/`;
  }